Driver's cognitive and psychological characteristics in an emergency during quasi-autonomous driving and the accident prevention based on artificial intelligence
| Project/Area Number |
17K01297
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Social systems engineering/Safety system
|
|---|
| Research Institution | Ritsumeikan University (2019-2020)
The University of Tokushima (2017-2018) |
|---|
Principal Investigator |
Kashihara Koji 立命館大学, 情報理工学部, 教授 (40463202)
|
|---|
| Project Period (FY) |
2017-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2020: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
|
|---|
| Keywords | 認知心理学 / 安全システム科学 / 生理心理学 / 人工知能 / 認知科学 |
|---|
| Outline of Final Research Achievements |
This study aimed at evaluating the brain activity (i.e., attention) and autonomic nervous activity (i.e., stress and tension) of the driver in an emergency (e.g., suddenly running out and appearance of obstacles) during quasi-autonomous driving. By applying artificial intelligence and machine learning to the biometric data obtained from experiments, I proposed a technical method to reduce traffic accidents in quasi-autonomous driving and build a safe traffic environment. I also examined the high accuracy of an analysis method (i.e., time-frequency analysis) to predict and detect sudden seizures (i.e., abnormal conditions) from EEG signals. Moreover, the optimal route search by deep reinforcement learning was performed under the movement of multiple vehicles (including the driver's drowsiness and impatience), and it would become effective even in ever-changing traffic conditions.
|
| Academic Significance and Societal Importance of the Research Achievements |
緊急時に自動から手動運転に切り替わる準自動運転では、運転者の眠気やよそ見等（注意力の欠如）が重大事故に繋がる。従って、準自動運転中の認知心理特性を把握し、緊急時に即座に対応できる手法の検討が重要となる。特に、緊急事態での運転者の認知心理特性に基づき、注意喚起が可能なブレイン・コンピュータインタフェースを実現できれば、準自動運転のみならず、通常運転での警告システムにも応用できる。また、高速道路の自動運転では、複雑な交通環境の変化を瞬時に把握し、安全かつ効率の良い走行経路を素早く決定する必要がある。カーナビや交通ニュース、交通管制センターからの指示等を用いれば、適切な対処法をフィードバックできる。
|
Report
(5 results)
Research Products
(20 results)
